skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/auto-estimate-generator/Gen Agent Trust Hub
auto-estimate-generator
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements legitimate data processing logic for construction estimation. No malicious patterns such as remote code execution, obfuscation, or data exfiltration were found.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection via data ingestion from external files. 1. Ingestion points: Data ingestion occurs in
SKILL.mdvia theload_pricing_rules_from_dfandload_qto_from_dfmethods which parse CSV or Excel data. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in theinstructions.mdfile. 3. Capability inventory: The skill usesfilesystempermissions to export data to Excel usingopenpyxl. No network or system-level command execution capabilities are present. 4. Sanitization: The skill performs type conversion for numeric and enum fields, but no textual sanitization is applied to input strings before they are processed or output.
Audit Metadata